From: 011netservice@gmail.com
Date: 2024-03-04, 週1
Subject: CodeHelper\cs\KeyWord\Encodings.txt

#### GetByteCount, GetMaxByteCount, 
using System;
using System.Text;

public class SamplesEncoding  {

   public static void Main()  {

      // The characters to encode:
      //    Latin Small Letter Z (U+007A)
      //    Latin Small Letter A (U+0061)
      //    Combining Breve (U+0306)
      //    Latin Small Letter AE With Acute (U+01FD)
      //    Greek Small Letter Beta (U+03B2)
      //    a high-surrogate value (U+D8FF)
      //    a low-surrogate value (U+DCFF)
      String myStr = "za\u0306\u01FD\u03B2\uD8FF\uDCFF";

      // Get different encodings.
      Encoding  u7    = Encoding.UTF7;
      Encoding  u8    = Encoding.UTF8;
      Encoding  u16LE = Encoding.Unicode;
      Encoding  u16BE = Encoding.BigEndianUnicode;
      Encoding  u32   = Encoding.UTF32;

      // Encode the entire string, and print out the counts and the resulting bytes.
      Console.WriteLine( "Encoding the entire string:" );
      PrintCountsAndBytes( myStr, u7 );
      PrintCountsAndBytes( myStr, u8 );
      PrintCountsAndBytes( myStr, u16LE );
      PrintCountsAndBytes( myStr, u16BE );
      PrintCountsAndBytes( myStr, u32 );

      Console.WriteLine();

      // Encode three characters starting at index 4, and print out the counts and the resulting bytes.
      Console.WriteLine( "Encoding the characters from index 4 through 6:" );
      PrintCountsAndBytes( myStr, 4, 3, u7 );
      PrintCountsAndBytes( myStr, 4, 3, u8 );
      PrintCountsAndBytes( myStr, 4, 3, u16LE );
      PrintCountsAndBytes( myStr, 4, 3, u16BE );
      PrintCountsAndBytes( myStr, 4, 3, u32 );
   }

   public static void PrintCountsAndBytes( String s, Encoding enc )  {

      // Display the name of the encoding used.
      Console.Write( "{0,-30} :", enc.ToString() );

      // Display the exact byte count.
      int iBC  = enc.GetByteCount( s );
      Console.Write( " {0,-3}", iBC );

      // Display the maximum byte count.
      int iMBC = enc.GetMaxByteCount( s.Length );
      Console.Write( " {0,-3} :", iMBC );

      // Encode the entire string.
      byte[] bytes = enc.GetBytes( s );

      // Display all the encoded bytes.
      PrintHexBytes( bytes );
   }

   public static void PrintCountsAndBytes( String s, int index, int count, Encoding enc )  {

      // Display the name of the encoding used.
      Console.Write( "{0,-30} :", enc.ToString() );

      // Display the exact byte count.
      int iBC  = enc.GetByteCount( s.ToCharArray(), index, count );
      Console.Write( " {0,-3}", iBC );

      // Display the maximum byte count.
      int iMBC = enc.GetMaxByteCount( count );
      Console.Write( " {0,-3} :", iMBC );

      // Encode a range of characters in the string.
      byte[] bytes = new byte[iBC];
      enc.GetBytes( s, index, count, bytes, bytes.GetLowerBound(0) );

      // Display all the encoded bytes.
      PrintHexBytes( bytes );
   }

   public static void PrintHexBytes( byte[] bytes )  {

      if (( bytes == null ) || ( bytes.Length == 0 ))
        {
            Console.WriteLine( "<none>" );
        }
        else  {
         for ( int i = 0; i < bytes.Length; i++ )
            Console.Write( "{0:X2} ", bytes[i] );
         Console.WriteLine();
      }
   }
}

/* 
      String myStr = "za\u0306\u01FD\u03B2\uD8FF\uDCFF";
This code produces the following output.

Encoding the entire string:
System.Text.UTF7Encoding       : 18  23  :7A 61 2B 41 77 59 42 2F 51 4F 79 32 50 2F 63 2F 77 2D
System.Text.UTF8Encoding       : 12  24  :7A 61 CC 86 C7 BD CE B2 F1 8F B3 BF
System.Text.UnicodeEncoding    : 14  16  :7A 00 61 00 06 03 FD 01 B2 03 FF D8 FF DC
System.Text.UnicodeEncoding    : 14  16  :00 7A 00 61 03 06 01 FD 03 B2 D8 FF DC FF
System.Text.UTF32Encoding      : 24  32  :7A 00 00 00 61 00 00 00 06 03 00 00 FD 01 00 00 B2 03 00 00 FF FC 04 00

Encoding the characters from index 4 through 6:
System.Text.UTF7Encoding       : 10  11  :2B 41 37 4C 59 2F 39 7A 2F 2D
System.Text.UTF8Encoding       : 6   12  :CE B2 F1 8F B3 BF
System.Text.UnicodeEncoding    : 6   8   :B2 03 FF D8 FF DC
System.Text.UnicodeEncoding    : 6   8   :03 B2 D8 FF DC FF
System.Text.UTF32Encoding      : 8   16  :B2 03 00 00 FF FC 04 00

*/


#### Unicode

The Unicode Standard assigns a code point (a number) to each character in every supported script. 
A Unicode Transformation Format (UTF) is a way to encode that code point. 
The Unicode Standard uses the following UTFs:

UTF-8, (1 到 4 byte) which represents each code point as a sequence of one to four bytes.
UTF-16,(2 或 4 byte, 即 1 到 2 個 16-bit integer) which represents each code point as a sequence of one to two 16-bit integers.
UTF-32,(固定 4 byte) which represents each code point as a 32-bit integer.

For more information about the UTFs and other encodings supported by System.Text, see Character Encoding in the .NET Framework.

The UnicodeEncoding class represents a UTF-16 encoding. The encoder can use either big endian byte order (most significant byte first) or little endian byte order (least significant byte first). For example, the Latin Capital Letter A (code point U+0041) is serialized as follows (in hexadecimal):

Big endian byte order: 00 00 00 41

Little endian byte order: 41 00 00 00


#### CodePages
    常用 CodePage, CodeName, Description, 
    ------ ------------ ----------------------------
    936,   gb2312,      Chinese Simplified (GB2312)            
    950,   big5,        Chinese Traditional (Big5)  
    1200,  utf-16,      Unicode                     
    1201,  unicodeFFFE, Unicode (Big-Endian)        
    20127, us-ascii,    US-ASCII                    
    65001, utf-8,       Unicode (UTF-8)             
    ------ ------------ ----------------------------

    The example produces the following output when run on .NET Core:

    Info.CodePage      Info.Name                    Info.DisplayName
    1200               utf-16                       Unicode                      
    1201               utf-16BE                     Unicode (Big-Endian)         
    12000              utf-32                       Unicode (UTF-32)             
    12001              utf-32BE                     Unicode (UTF-32 Big-Endian)    
    20127              us-ascii                     US-ASCII                     
    28591              iso-8859-1                   Western European (ISO)       
    65000              utf-7                        Unicode (UTF-7)              
    65001              utf-8                        Unicode (UTF-8)              

    The example produces the following output when run on .NET Framework:

    Info.CodePage      Info.Name                    Info.DisplayName
    37                 IBM037                       IBM EBCDIC (US-Canada)       
    437                IBM437                       OEM United States            
    500                IBM500                       IBM EBCDIC (International)    
    708                ASMO-708                     Arabic (ASMO 708)            
    720                DOS-720                      Arabic (DOS)                 
    737                ibm737                       Greek (DOS)                  
    775                ibm775                       Baltic (DOS)                 
    850                ibm850                       Western European (DOS)       
    852                ibm852                       Central European (DOS)       
    855                IBM855                       OEM Cyrillic                 
    857                ibm857                       Turkish (DOS)                
    858                IBM00858                     OEM Multilingual Latin I     
    860                IBM860                       Portuguese (DOS)             
    861                ibm861                       Icelandic (DOS)              
    862                DOS-862                      Hebrew (DOS)                 
    863                IBM863                       French Canadian (DOS)        
    864                IBM864                       Arabic (864)                 
    865                IBM865                       Nordic (DOS)                 
    866                cp866                        Cyrillic (DOS)               
    869                ibm869                       Greek, Modern (DOS)          
    870                IBM870                       IBM EBCDIC (Multilingual Latin-2)    
    874                windows-874                  Thai (Windows)               
    875                cp875                        IBM EBCDIC (Greek Modern)    
    932                shift_jis                    Japanese (Shift-JIS)         
    936                gb2312                       Chinese Simplified (GB2312)      
    949                ks_c_5601-1987               Korean                       
    950                big5                         Chinese Traditional (Big5)    
    1026               IBM1026                      IBM EBCDIC (Turkish Latin-5)    
    1047               IBM01047                     IBM Latin-1                  
    1140               IBM01140                     IBM EBCDIC (US-Canada-Euro)    
    1141               IBM01141                     IBM EBCDIC (Germany-Euro)    
    1142               IBM01142                     IBM EBCDIC (Denmark-Norway-Euro)    
    1143               IBM01143                     IBM EBCDIC (Finland-Sweden-Euro)    
    1144               IBM01144                     IBM EBCDIC (Italy-Euro)      
    1145               IBM01145                     IBM EBCDIC (Spain-Euro)      
    1146               IBM01146                     IBM EBCDIC (UK-Euro)         
    1147               IBM01147                     IBM EBCDIC (France-Euro)     
    1148               IBM01148                     IBM EBCDIC (International-Euro)    
    1149               IBM01149                     IBM EBCDIC (Icelandic-Euro)    
    1200               utf-16                       Unicode                      
    1201               utf-16BE                     Unicode (Big-Endian)         
    1250               windows-1250                 Central European (Windows)    
    1251               windows-1251                 Cyrillic (Windows)           
    1252               Windows-1252                 Western European (Windows)    
    1253               windows-1253                 Greek (Windows)              
    1254               windows-1254                 Turkish (Windows)            
    1255               windows-1255                 Hebrew (Windows)             
    1256               windows-1256                 Arabic (Windows)             
    1257               windows-1257                 Baltic (Windows)             
    1258               windows-1258                 Vietnamese (Windows)         
    1361               Johab                        Korean (Johab)               
    10000              macintosh                    Western European (Mac)       
    10001              x-mac-japanese               Japanese (Mac)               
    10002              x-mac-chinesetrad            Chinese Traditional (Mac)    
    10003              x-mac-korean                 Korean (Mac)                 
    10004              x-mac-arabic                 Arabic (Mac)                 
    10005              x-mac-hebrew                 Hebrew (Mac)                 
    10006              x-mac-greek                  Greek (Mac)                  
    10007              x-mac-cyrillic               Cyrillic (Mac)               
    10008              x-mac-chinesesimp            Chinese Simplified (Mac)     
    10010              x-mac-romanian               Romanian (Mac)               
    10017              x-mac-ukrainian              Ukrainian (Mac)              
    10021              x-mac-thai                   Thai (Mac)                   
    10029              x-mac-ce                     Central European (Mac)       
    10079              x-mac-icelandic              Icelandic (Mac)              
    10081              x-mac-turkish                Turkish (Mac)                
    10082              x-mac-croatian               Croatian (Mac)               
    12000              utf-32                       Unicode (UTF-32)             
    12001              utf-32BE                     Unicode (UTF-32 Big-Endian)    
    20000              x-Chinese-CNS                Chinese Traditional (CNS)    
    20001              x-cp20001                    TCA Taiwan                   
    20002              x-Chinese-Eten               Chinese Traditional (Eten)    
    20003              x-cp20003                    IBM5550 Taiwan               
    20004              x-cp20004                    TeleText Taiwan              
    20005              x-cp20005                    Wang Taiwan                  
    20105              x-IA5                        Western European (IA5)       
    20106              x-IA5-German                 German (IA5)                 
    20107              x-IA5-Swedish                Swedish (IA5)                
    20108              x-IA5-Norwegian              Norwegian (IA5)              
    20127              us-ascii                     US-ASCII                     
    20261              x-cp20261                    T.61                         
    20269              x-cp20269                    ISO-6937                     
    20273              IBM273                       IBM EBCDIC (Germany)         
    20277              IBM277                       IBM EBCDIC (Denmark-Norway)    
    20278              IBM278                       IBM EBCDIC (Finland-Sweden)    
    20280              IBM280                       IBM EBCDIC (Italy)           
    20284              IBM284                       IBM EBCDIC (Spain)           
    20285              IBM285                       IBM EBCDIC (UK)              
    20290              IBM290                       IBM EBCDIC (Japanese katakana)    
    20297              IBM297                       IBM EBCDIC (France)          
    20420              IBM420                       IBM EBCDIC (Arabic)          
    20423              IBM423                       IBM EBCDIC (Greek)           
    20424              IBM424                       IBM EBCDIC (Hebrew)          
    20833              x-EBCDIC-KoreanExtended      IBM EBCDIC (Korean Extended)    
    20838              IBM-Thai                     IBM EBCDIC (Thai)            
    20866              koi8-r                       Cyrillic (KOI8-R)            
    20871              IBM871                       IBM EBCDIC (Icelandic)       
    20880              IBM880                       IBM EBCDIC (Cyrillic Russian)    
    20905              IBM905                       IBM EBCDIC (Turkish)         
    20924              IBM00924                     IBM Latin-1                  
    20932              EUC-JP                       Japanese (JIS 0208-1990 and 0212-1990)    
    20936              x-cp20936                    Chinese Simplified (GB2312-80)    
    20949              x-cp20949                    Korean Wansung               
    21025              cp1025                       IBM EBCDIC (Cyrillic Serbian-Bulgarian)    
    21866              koi8-u                       Cyrillic (KOI8-U)            
    28591              iso-8859-1                   Western European (ISO)       
    28592              iso-8859-2                   Central European (ISO)       
    28593              iso-8859-3                   Latin 3 (ISO)                
    28594              iso-8859-4                   Baltic (ISO)                 
    28595              iso-8859-5                   Cyrillic (ISO)               
    28596              iso-8859-6                   Arabic (ISO)                 
    28597              iso-8859-7                   Greek (ISO)                  
    28598              iso-8859-8                   Hebrew (ISO-Visual)          
    28599              iso-8859-9                   Turkish (ISO)                
    28603              iso-8859-13                  Estonian (ISO)               
    28605              iso-8859-15                  Latin 9 (ISO)                
    29001              x-Europa                     Europa                       
    38598              iso-8859-8-i                 Hebrew (ISO-Logical)         
    50220              iso-2022-jp                  Japanese (JIS)               
    50221              csISO2022JP                  Japanese (JIS-Allow 1 byte Kana)    
    50222              iso-2022-jp                  Japanese (JIS-Allow 1 byte Kana - SO/SI)    
    50225              iso-2022-kr                  Korean (ISO)                 
    50227              x-cp50227                    Chinese Simplified (ISO-2022)    
    51932              euc-jp                       Japanese (EUC)               
    51936              EUC-CN                       Chinese Simplified (EUC)     
    51949              euc-kr                       Korean (EUC)                 
    52936              hz-gb-2312                   Chinese Simplified (HZ)      
    54936              GB18030                      Chinese Simplified (GB18030)    
    57002              x-iscii-de                   ISCII Devanagari             
    57003              x-iscii-be                   ISCII Bengali                
    57004              x-iscii-ta                   ISCII Tamil                  
    57005              x-iscii-te                   ISCII Telugu                 
    57006              x-iscii-as                   ISCII Assamese               
    57007              x-iscii-or                   ISCII Oriya                  
    57008              x-iscii-ka                   ISCII Kannada                
    57009              x-iscii-ma                   ISCII Malayalam              
    57010              x-iscii-gu                   ISCII Gujarati               
    57011              x-iscii-pa                   ISCII Punjabi                
    65000              utf-7                        Unicode (UTF-7)              
    65001              utf-8                        Unicode (UTF-8)   

#### Encoding.ASCII  
Gets an encoding for the ASCII (7-bit) character set.
public static System.Text.Encoding ASCII { get; }
ASCII 限制為最低的 128 個 Unicode 字元, 從 U+0000 到 U+007F。
以下範例若無法轉換為 ASCII 的字元, 會被替換為 "?"

The following example demonstrates the effect of the ASCII encoding on characters that are outside the ASCII range.

using System;
using System.Text;

class EncodingExample 
{
  public static void Main() 
  {
      // Create an ASCII encoding.
      Encoding ascii = Encoding.ASCII;
  
      // A Unicode string with two characters outside the ASCII code range.
      String unicodeString =
          "This unicode string contains two characters " +
          "with codes outside the ASCII code range, " +
          "Pi (\u03a0) and Sigma (\u03a3).";
      Console.WriteLine("Original string:");
      Console.WriteLine(unicodeString);

      // Save the positions of the special characters for later reference.
      int indexOfPi = unicodeString.IndexOf('\u03a0');
      int indexOfSigma = unicodeString.IndexOf('\u03a3');

      // Encode the string.
      Byte[] encodedBytes = ascii.GetBytes(unicodeString);
      Console.WriteLine();
      Console.WriteLine("Encoded bytes:");
      foreach (Byte b in encodedBytes) 
      {
          Console.Write("[{0}]", b);
      }
      Console.WriteLine();
  
      // Notice that the special characters have been replaced with
      // the value 63, which is the ASCII character code for '?'.
      Console.WriteLine();
      Console.WriteLine(
          "Value at position of Pi character: {0}",
          encodedBytes[indexOfPi]
          );
      Console.WriteLine(
          "Value at position of Sigma character: {0}",
          encodedBytes[indexOfSigma]
          );

      // Decode bytes back to a string.
      // Notice missing the Pi and Sigma characters.
      String decodedString = ascii.GetString(encodedBytes);
      Console.WriteLine();
      Console.WriteLine("Decoded bytes:");
      Console.WriteLine(decodedString);
  }
}
/*
This code produces the following output.

Original string:
This unicode string contains two characters with codes outside the ASCII code range, Pi (Π) and Sigma (Σ).

Encoded bytes:
[84][104][105][115][32][117][110][105][99][111][100][101][32][115][116][114][105][110][103][32][99][111][110][116][97][105][110][115][32][116][119][111][32][99][104][97][114][97][99][116][101][114][115][32][119][105][116][104][32][99][111][100][101][115][32][111][117][116][115][105][100][101][32][116][104][101][32][65][83][67][73][73][32][99][111][100][101][32][114][97][110][103][101][44][32][80][105][32][40][63][41][32][97][110][100][32][83][105][103][109][97][32][40][63][41][46]

Value at position of Pi character: 63
Value at position of Sigma character: 63

Decoded bytes:
This unicode string contains two characters with codes outside the ASCII code range, Pi (?) and Sigma (?).

*/

Remarks
ASCII characters are limited to the lowest 128 Unicode characters, from U+0000 to U+007F.
ASCII 限制為最低的 128 個 Unicode 字元, 從 U+0000 到 U+007F。

When selecting the ASCII encoding for your app, consider the following:

1. The ASCII encoding is usually appropriate for protocols that require ASCII.

2. If you require 8-bit encoding (which is sometimes incorrectly referred to as "ASCII"), 
the UTF-8 encoding is recommended over the ASCII encoding. 
For the characters 0-7F, the results are identical, but use of UTF-8 avoids data loss by allowing representation of all Unicode characters that are representable. 
Note that the ASCII encoding has an 8th bit ambiguity that can allow malicious use, but the UTF-8 encoding removes ambiguity about the 8th bit.

3. Prior to .NET Framework version 2.0, .NET Framework allowed spoofing by ignoring the 8th bit. 
Beginning with .NET Framework 2.0, non-ASCII code points fall back during decoding.

The ASCIIEncoding object that is returned by this property might not have the appropriate behavior for your app. 
It uses replacement fallback to replace each string that it cannot encode and each byte that it cannot decode with a question mark ("?") character. 
Instead, you can call the GetEncoding(String, EncoderFallback, DecoderFallback) method to instantiate an ASCIIEncoding object whose fallback is either an EncoderFallbackException or a DecoderFallbackException, 
as the following example illustrates.

以下 ASCII 程式碼轉換, 若無法轉換時, 則會拋出 exception, 不會另行轉換為"?"
using System;
using System.Text;

public class Example
{
   public static void Main()
   {
      Encoding enc = Encoding.GetEncoding("us-ascii", 
                                          new EncoderExceptionFallback(),
                                          new DecoderExceptionFallback());
      string value = "\u00C4 \u00F6 \u00AE"; 
      
      try {
         byte[] bytes= enc.GetBytes(value);
         foreach (var byt in bytes)
            Console.Write("{0:X2} ", byt);
         Console.WriteLine();

         string value2 = enc.GetString(bytes);
         Console.WriteLine(value2);
      }
      catch (EncoderFallbackException e) {
         Console.WriteLine("Unable to encode {0} at index {1}", 
                           e.IsUnknownSurrogate() ? 
                              String.Format("U+{0:X4} U+{1:X4}", 
                                            Convert.ToUInt16(e.CharUnknownHigh),
                                            Convert.ToUInt16(e.CharUnknownLow)) :
                              String.Format("U+{0:X4}", 
                                            Convert.ToUInt16(e.CharUnknown)),
                           e.Index);
      }
   }
}
// The example displays the following output:
//        Unable to encode U+00C4 at index 0



#### Example: Decode Unicode
https://learn.microsoft.com/en-us/dotnet/api/system.text.decoder.getchars?view=net-8.0
The following example demonstrates how to decode a range of elements from a byte array and store them in a Unicode character array. 
The GetCharCount method is used to calculate the number of characters needed to store the decoded elements in the array bytes. 
The GetChars method decodes the specified elements in the byte array and stores them in the new character array.
using System;
using System.Text;

class UnicodeEncodingExample {
    public static void Main() {
        Char[] chars;
		
		// 備忘: Unicode 跟 c 的 string 結尾為 0 會衝突:
        Byte[] bytes = new Byte[] { 85, 0, 110, 0, 105, 0, 99, 0, 111, 0, 100, 0, 101, 0};

        Decoder uniDecoder = Encoding.Unicode.GetDecoder();

        int charCount = uniDecoder.GetCharCount(bytes, 0, bytes.Length); // 取得 char 個數.
        chars = new Char[charCount]; // 宣告剛好符合大小的 char[] buffer.
        int charsDecodedCount = uniDecoder.GetChars(bytes, 0, bytes.Length, chars, 0); // copy bytes to chars.

        Console.WriteLine(
            "{0} characters used to decode bytes.", charsDecodedCount
        );

        Console.Write("Decoded chars: ");
        foreach (Char c in chars) {
            Console.Write("[{0}]", c);
        }
        Console.WriteLine();
    }
}

 This code example produces the following output.

7 characters used to decode bytes.
Decoded chars: [U][n][i][c][o][d][e]




#### Example: converts a string from one encoding to another
https://learn.microsoft.com/en-us/dotnet/api/system.text.encoding.getcharcount?view=net-8.0#system-text-encoding-getcharcount(system-byte()-system-int32-system-int32)

The following example converts a string from one encoding to another.
using System;
using System.Text;

class Example
{
   static void Main()
   {
      string unicodeString = "This string contains the unicode character Pi (\u03a0)";

      // Create two different encodings.
      Encoding ascii = Encoding.ASCII;
      Encoding unicode = Encoding.Unicode;

      // Convert the string into a byte array.
      byte[] unicodeBytes = unicode.GetBytes(unicodeString);

      // Perform the conversion from one encoding to the other.
      byte[] asciiBytes = Encoding.Convert(unicode, ascii, unicodeBytes);
         
      // Convert the new byte[] into a char[] and then into a string.
      char[] asciiChars = new char[ascii.GetCharCount(asciiBytes, 0, asciiBytes.Length)];
      ascii.GetChars(asciiBytes, 0, asciiBytes.Length, asciiChars, 0);
      string asciiString = new string(asciiChars);

      // Display the strings created before and after the conversion.
      Console.WriteLine("Original string: {0}", unicodeString);
      Console.WriteLine("Ascii converted string: {0}", asciiString);
   }
}
// The example displays the following output:
//    Original string: This string contains the unicode character Pi (Π)
//    Ascii converted string: This string contains the unicode character Pi (?)




#### Example: encodes a string and decodes a range of bytes.
https://learn.microsoft.com/en-us/dotnet/api/system.text.encoding.getcharcount?view=net-8.0#system-text-encoding-getcharcount(system-byte()-system-int32-system-int32)
The following example encodes a string into an array of bytes, 
and then decodes a range of the bytes into an array of characters.
 
using System;
using System.Text;

public class SamplesEncoding  {

   public static void Main()  {

      // Create two instances of UTF32Encoding: one with little-endian byte order and one with big-endian byte order.
      Encoding u32LE = Encoding.GetEncoding( "utf-32" );
      Encoding u32BE = Encoding.GetEncoding( "utf-32BE" );

      // Use a string containing the following characters:
      //    Latin Small Letter Z (U+007A)
      //    Latin Small Letter A (U+0061)
      //    Combining Breve (U+0306)
      //    Latin Small Letter AE With Acute (U+01FD)
      //    Greek Small Letter Beta (U+03B2)
      String myStr = "za\u0306\u01FD\u03B2";

      // Encode the string using the big-endian byte order.
      byte[] barrBE = new byte[u32BE.GetByteCount( myStr )];
      u32BE.GetBytes( myStr, 0, myStr.Length, barrBE, 0 );

      // Encode the string using the little-endian byte order.
      byte[] barrLE = new byte[u32LE.GetByteCount( myStr )];
      u32LE.GetBytes( myStr, 0, myStr.Length, barrLE, 0 );

      // Get the char counts, decode eight bytes starting at index 0,
      // and print out the counts and the resulting bytes.
      Console.Write( "BE array with BE encoding : " );
      PrintCountsAndChars( barrBE, 0, 8, u32BE );
      Console.Write( "LE array with LE encoding : " );
      PrintCountsAndChars( barrLE, 0, 8, u32LE );
   }

   public static void PrintCountsAndChars( byte[] bytes, int index, int count, Encoding enc )  {

      // Display the name of the encoding used.
      Console.Write( "{0,-25} :", enc.ToString() );

      // Display the exact character count.
      int iCC  = enc.GetCharCount( bytes, index, count );
      Console.Write( " {0,-3}", iCC );

      // Display the maximum character count.
      int iMCC = enc.GetMaxCharCount( count );
      Console.Write( " {0,-3} :", iMCC );

      // Decode the bytes and display the characters.
      char[] chars = enc.GetChars( bytes, index, count );

      // The following is an alternative way to decode the bytes:
      // char[] chars = new char[iCC];
      // enc.GetChars( bytes, index, count, chars, 0 );

      Console.WriteLine( chars );
   }
}


 
This code produces the following output.  The question marks take the place of characters that cannot be displayed at the console.

BE array with BE encoding : System.Text.UTF32Encoding : 2   6   :za
LE array with LE encoding : System.Text.UTF32Encoding : 2   6   :za





#### 以下舊資料確認後移到上面
----------
using System;
using System.Text;

public class SamplesEncoding  {

   public static void Main()  {

      // Print the header.
      Console.Write( "Name               " );
      Console.Write( "CodePage  " );
      Console.Write( "BodyName           " );
      Console.Write( "HeaderName         " );
      Console.Write( "WebName            " );
      Console.WriteLine( "Encoding.EncodingName" );

      // For every encoding, compare the name properties with EncodingInfo.Name.
      // Display only the encodings that have one or more different names.
      foreach( EncodingInfo ei in Encoding.GetEncodings() )  {
         Encoding e = ei.GetEncoding();

         if (( ei.Name != e.BodyName ) || ( ei.Name != e.HeaderName ) || ( ei.Name != e.WebName ))  {
            Console.Write( "{0,-18} ", ei.Name );
            Console.Write( "{0,-9} ",  e.CodePage );
            Console.Write( "{0,-18} ", e.BodyName );
            Console.Write( "{0,-18} ", e.HeaderName );
            Console.Write( "{0,-18} ", e.WebName );
            Console.WriteLine( "{0} ", e.EncodingName );
         }

      }

   }

}


/* 
This code produces the following output.

Name               CodePage  BodyName           HeaderName         WebName            Encoding.EncodingName
shift_jis          932       iso-2022-jp        iso-2022-jp        shift_jis          Japanese (Shift-JIS)
windows-1250       1250      iso-8859-2         windows-1250       windows-1250       Central European (Windows)
windows-1251       1251      koi8-r             windows-1251       windows-1251       Cyrillic (Windows)
Windows-1252       1252      iso-8859-1         Windows-1252       Windows-1252       Western European (Windows)
windows-1253       1253      iso-8859-7         windows-1253       windows-1253       Greek (Windows)
windows-1254       1254      iso-8859-9         windows-1254       windows-1254       Turkish (Windows)
csISO2022JP        50221     iso-2022-jp        iso-2022-jp        csISO2022JP        Japanese (JIS-Allow 1 byte Kana)
iso-2022-kr        50225     iso-2022-kr        euc-kr             iso-2022-kr        Korean (ISO)

*/

----------
using System;
using System.Text;

public class SamplesEncoding  {

   public static void Main()  {

      // Print the header.
      Console.Write( "CodePage identifier and name     " );
      Console.Write( "BrDisp   BrSave   " );
      Console.Write( "MNDisp   MNSave   " );
      Console.WriteLine( "1-Byte   ReadOnly " );

      // For every encoding, get the property values.
      foreach( EncodingInfo ei in Encoding.GetEncodings() )  {
         Encoding e = ei.GetEncoding();

         Console.Write( "{0,-6} {1,-25} ", ei.CodePage, ei.Name );
         Console.Write( "{0,-8} {1,-8} ", e.IsBrowserDisplay, e.IsBrowserSave );
         Console.Write( "{0,-8} {1,-8} ", e.IsMailNewsDisplay, e.IsMailNewsSave );
         Console.WriteLine( "{0,-8} {1,-8} ", e.IsSingleByte, e.IsReadOnly );
      }

   }

}


/* 
This code produces the following output.

CodePage identifier and name     BrDisp   BrSave   MNDisp   MNSave   1-Byte   ReadOnly 
37     IBM037                    False    False    False    False    True     True     
437    IBM437                    False    False    False    False    True     True     
500    IBM500                    False    False    False    False    True     True     
708    ASMO-708                  True     True     False    False    True     True     
720    DOS-720                   True     True     False    False    True     True     
737    ibm737                    False    False    False    False    True     True     
775    ibm775                    False    False    False    False    True     True     
850    ibm850                    False    False    False    False    True     True     
852    ibm852                    True     True     False    False    True     True     
855    IBM855                    False    False    False    False    True     True     
857    ibm857                    False    False    False    False    True     True     
858    IBM00858                  False    False    False    False    True     True     
860    IBM860                    False    False    False    False    True     True     
861    ibm861                    False    False    False    False    True     True     
862    DOS-862                   True     True     False    False    True     True     
863    IBM863                    False    False    False    False    True     True     
864    IBM864                    False    False    False    False    True     True     
865    IBM865                    False    False    False    False    True     True     
866    cp866                     True     True     False    False    True     True     
869    ibm869                    False    False    False    False    True     True     
870    IBM870                    False    False    False    False    True     True     
874    windows-874               True     True     True     True     True     True     
875    cp875                     False    False    False    False    True     True     
932    shift_jis                 True     True     True     True     False    True     
936    gb2312                    True     True     True     True     False    True     
949    ks_c_5601-1987            True     True     True     True     False    True     
950    big5                      True     True     True     True     False    True     
1026   IBM1026                   False    False    False    False    True     True     
1047   IBM01047                  False    False    False    False    True     True     
1140   IBM01140                  False    False    False    False    True     True     
1141   IBM01141                  False    False    False    False    True     True     
1142   IBM01142                  False    False    False    False    True     True     
1143   IBM01143                  False    False    False    False    True     True     
1144   IBM01144                  False    False    False    False    True     True     
1145   IBM01145                  False    False    False    False    True     True     
1146   IBM01146                  False    False    False    False    True     True     
1147   IBM01147                  False    False    False    False    True     True     
1148   IBM01148                  False    False    False    False    True     True     
1149   IBM01149                  False    False    False    False    True     True     
1200   utf-16                    False    True     False    False    False    True     
1201   unicodeFFFE               False    False    False    False    False    True     
1250   windows-1250              True     True     True     True     True     True     
1251   windows-1251              True     True     True     True     True     True     
1252   Windows-1252              True     True     True     True     True     True     
1253   windows-1253              True     True     True     True     True     True     
1254   windows-1254              True     True     True     True     True     True     
1255   windows-1255              True     True     True     True     True     True     
1256   windows-1256              True     True     True     True     True     True     
1257   windows-1257              True     True     True     True     True     True     
1258   windows-1258              True     True     True     True     True     True     
1361   Johab                     False    False    False    False    False    True     
10000  macintosh                 False    False    False    False    True     True     
10001  x-mac-japanese            False    False    False    False    False    True     
10002  x-mac-chinesetrad         False    False    False    False    False    True     
10003  x-mac-korean              False    False    False    False    False    True     
10004  x-mac-arabic              False    False    False    False    True     True     
10005  x-mac-hebrew              False    False    False    False    True     True     
10006  x-mac-greek               False    False    False    False    True     True     
10007  x-mac-cyrillic            False    False    False    False    True     True     
10008  x-mac-chinesesimp         False    False    False    False    False    True     
10010  x-mac-romanian            False    False    False    False    True     True     
10017  x-mac-ukrainian           False    False    False    False    True     True     
10021  x-mac-thai                False    False    False    False    True     True     
10029  x-mac-ce                  False    False    False    False    True     True     
10079  x-mac-icelandic           False    False    False    False    True     True     
10081  x-mac-turkish             False    False    False    False    True     True     
10082  x-mac-croatian            False    False    False    False    True     True     
12000  utf-32                    False    False    False    False    False    True     
12001  utf-32BE                  False    False    False    False    False    True     
20000  x-Chinese-CNS             False    False    False    False    False    True     
20001  x-cp20001                 False    False    False    False    False    True     
20002  x-Chinese-Eten            False    False    False    False    False    True     
20003  x-cp20003                 False    False    False    False    False    True     
20004  x-cp20004                 False    False    False    False    False    True     
20005  x-cp20005                 False    False    False    False    False    True     
20105  x-IA5                     False    False    False    False    True     True     
20106  x-IA5-German              False    False    False    False    True     True     
20107  x-IA5-Swedish             False    False    False    False    True     True     
20108  x-IA5-Norwegian           False    False    False    False    True     True     
20127  us-ascii                  False    False    True     True     True     True     
20261  x-cp20261                 False    False    False    False    False    True     
20269  x-cp20269                 False    False    False    False    True     True     
20273  IBM273                    False    False    False    False    True     True     
20277  IBM277                    False    False    False    False    True     True     
20278  IBM278                    False    False    False    False    True     True     
20280  IBM280                    False    False    False    False    True     True     
20284  IBM284                    False    False    False    False    True     True     
20285  IBM285                    False    False    False    False    True     True     
20290  IBM290                    False    False    False    False    True     True     
20297  IBM297                    False    False    False    False    True     True     
20420  IBM420                    False    False    False    False    True     True     
20423  IBM423                    False    False    False    False    True     True     
20424  IBM424                    False    False    False    False    True     True     
20833  x-EBCDIC-KoreanExtended   False    False    False    False    True     True     
20838  IBM-Thai                  False    False    False    False    True     True     
20866  koi8-r                    True     True     True     True     True     True     
20871  IBM871                    False    False    False    False    True     True     
20880  IBM880                    False    False    False    False    True     True     
20905  IBM905                    False    False    False    False    True     True     
20924  IBM00924                  False    False    False    False    True     True     
20932  EUC-JP                    False    False    False    False    False    True     
20936  x-cp20936                 False    False    False    False    False    True     
20949  x-cp20949                 False    False    False    False    False    True     
21025  cp1025                    False    False    False    False    True     True     
21866  koi8-u                    True     True     True     True     True     True     
28591  iso-8859-1                True     True     True     True     True     True     
28592  iso-8859-2                True     True     True     True     True     True     
28593  iso-8859-3                False    False    True     True     True     True     
28594  iso-8859-4                True     True     True     True     True     True     
28595  iso-8859-5                True     True     True     True     True     True     
28596  iso-8859-6                True     True     True     True     True     True     
28597  iso-8859-7                True     True     True     True     True     True     
28598  iso-8859-8                True     True     False    False    True     True     
28599  iso-8859-9                True     True     True     True     True     True     
28603  iso-8859-13               False    False    True     True     True     True     
28605  iso-8859-15               False    True     True     True     True     True     
29001  x-Europa                  False    False    False    False    True     True     
38598  iso-8859-8-i              True     True     True     True     True     True     
50220  iso-2022-jp               False    False    True     True     False    True     
50221  csISO2022JP               False    True     True     True     False    True     
50222  iso-2022-jp               False    False    False    False    False    True     
50225  iso-2022-kr               False    False    True     False    False    True     
50227  x-cp50227                 False    False    False    False    False    True     
51932  euc-jp                    True     True     True     True     False    True     
51936  EUC-CN                    False    False    False    False    False    True     
51949  euc-kr                    False    False    True     True     False    True     
52936  hz-gb-2312                True     True     True     True     False    True     
54936  GB18030                   True     True     True     True     False    True     
57002  x-iscii-de                False    False    False    False    False    True     
57003  x-iscii-be                False    False    False    False    False    True     
57004  x-iscii-ta                False    False    False    False    False    True     
57005  x-iscii-te                False    False    False    False    False    True     
57006  x-iscii-as                False    False    False    False    False    True     
57007  x-iscii-or                False    False    False    False    False    True     
57008  x-iscii-ka                False    False    False    False    False    True     
57009  x-iscii-ma                False    False    False    False    False    True     
57010  x-iscii-gu                False    False    False    False    False    True     
57011  x-iscii-pa                False    False    False    False    False    True     
65000  utf-7                     False    False    True     True     False    True     
65001  utf-8                     True     True     True     True     False    True     

*/